bvandeusenandClaude Opus 5.5
6a68bd75d9
#5766 "A root helper the agent can start, for a fixed set of maintenance actions and nothing else", milestone 514. The agent runs unprivileged under NoNewPrivileges, so it can't update or reboot its host. It now leaves a request in /var/lib/steward-agent/requests, the one path its unit lets it write; steward-maint.path starts maint.py as root, which reads it without following links, accepts only update, reboot, drain or undrain, deletes it, and writes the outcome to /var/lib/steward-maint/results. The agent (1.17.0) reports each new result state once as a `maintenance` event, re-checks pending updates when an update finishes, and says in its metadata whether the helper is installed. The units and the helper are served from one copy at /plugins/host_agent/files/<name> (a fixed list), and install.sh plus the install, provision and update playbooks all fetch them, replacing three inline copies of the unit. Update agent installs the helper on existing hosts; the Agent panel says under Manage agent whether it is there. Steward handing out jobs is #5767; the cadence is #5768. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
76 lines
3.6 KiB
Python
76 lines
3.6 KiB
Python
# plugins/host_agent/models.py
|
|
from __future__ import annotations
|
|
import uuid
|
|
from datetime import datetime, timezone
|
|
from sqlalchemy import Boolean, Column, String, DateTime, Float, ForeignKey, Integer, Text
|
|
from steward.models.base import Base
|
|
|
|
|
|
def _uuid() -> str:
|
|
return str(uuid.uuid4())
|
|
|
|
|
|
def _utcnow() -> datetime:
|
|
return datetime.now(timezone.utc)
|
|
|
|
|
|
class HostAgentRegistration(Base):
|
|
__tablename__ = "host_agent_registrations"
|
|
|
|
id = Column(String(36), primary_key=True, default=_uuid)
|
|
host_id = Column(String(36), ForeignKey("hosts.id", ondelete="CASCADE"),
|
|
unique=True, nullable=False)
|
|
token_hash = Column(String(64), nullable=False, unique=True, index=True)
|
|
token_created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|
|
agent_version = Column(String(32), nullable=True)
|
|
kernel = Column(String(128), nullable=True)
|
|
distro = Column(String(128), nullable=True)
|
|
arch = Column(String(32), nullable=True)
|
|
# Agent-reported primary IP. 45 chars = max textual IPv6 (no zone suffix).
|
|
host_ip = Column(String(45), nullable=True)
|
|
last_seen_at = Column(DateTime(timezone=True), nullable=True)
|
|
# How far this host's clock is from Steward's, in seconds, positive when
|
|
# the host is ahead, measured from the agent's sent_at on the newest post;
|
|
# and when that was. None until an agent that stamps its posts reports.
|
|
clock_offset_s = Column(Float, nullable=True)
|
|
clock_checked_at = Column(DateTime(timezone=True), nullable=True)
|
|
# What the package manager has waiting, from the agent's hourly check
|
|
# (agent ≥ 1.16.0, #5765). updates_security is None when the manager
|
|
# can't say; updates_error is why the last check failed.
|
|
updates_manager = Column(String(8), nullable=True)
|
|
updates_pending = Column(Integer, nullable=True)
|
|
updates_security = Column(Integer, nullable=True)
|
|
updates_checked_at = Column(DateTime(timezone=True), nullable=True)
|
|
updates_error = Column(String(200), nullable=True)
|
|
# Whether the host needs a reboot (None: it can't say), since when, and
|
|
# the packages that asked for it, comma-separated.
|
|
reboot_required = Column(Boolean, nullable=True)
|
|
reboot_required_since = Column(DateTime(timezone=True), nullable=True)
|
|
reboot_packages = Column(Text, nullable=True)
|
|
# Whether the host has the root maintenance helper (steward-maint.path and
|
|
# its request directory) that updates and reboots go through (#5766); None
|
|
# until an agent that says reports.
|
|
maint_helper = Column(Boolean, nullable=True)
|
|
created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|
|
updated_at = Column(DateTime(timezone=True), nullable=False,
|
|
default=_utcnow, onupdate=_utcnow)
|
|
|
|
|
|
class HostDowntime(Base):
|
|
"""A span a host's agent was away, and what the agent said it was (#5756).
|
|
|
|
kind is "reboot" (the host went down and came back), "agent_stop" (the
|
|
agent stopped; the host stayed up), "unclean" (the host came back from a
|
|
boot nobody announced: power loss or a crash) or "lost_contact" (the agent
|
|
ran but couldn't reach Steward). ended_at is None while it is going on.
|
|
"""
|
|
__tablename__ = "host_downtime"
|
|
|
|
id = Column(String(36), primary_key=True, default=_uuid)
|
|
host_id = Column(String(36), ForeignKey("hosts.id", ondelete="CASCADE"),
|
|
nullable=False, index=True)
|
|
kind = Column(String(16), nullable=False)
|
|
started_at = Column(DateTime(timezone=True), nullable=False)
|
|
ended_at = Column(DateTime(timezone=True), nullable=True)
|
|
created_at = Column(DateTime(timezone=True), nullable=False, default=_utcnow)
|